sync file-type support across upload/convert and fix collected_at timezone handling

internal/parser/archive.go

@@ -9,23 +9,38 @@ import (
 	"io"
 	"os"
 	"path/filepath"
+	"sort"
 	"strings"
+	"time"
 )
 
 const maxSingleFileSize = 10 * 1024 * 1024
 const maxZipArchiveSize = 50 * 1024 * 1024
 const maxGzipDecompressedSize = 50 * 1024 * 1024
 
+var supportedArchiveExt = map[string]struct{}{
+	".gz":  {},
+	".tgz": {},
+	".tar": {},
+	".zip": {},
+	".txt": {},
+	".log": {},
+}
+
 // ExtractedFile represents a file extracted from archive
 type ExtractedFile struct {
 	Path             string
 	Content          []byte
+	ModTime          time.Time
 	Truncated        bool
 	TruncatedMessage string
 }
 
 // ExtractArchive extracts tar.gz or zip archive and returns file contents
 func ExtractArchive(archivePath string) ([]ExtractedFile, error) {
+	if !IsSupportedArchiveFilename(archivePath) {
+		return nil, fmt.Errorf("unsupported archive format: %s", strings.ToLower(filepath.Ext(archivePath)))
+	}
 	ext := strings.ToLower(filepath.Ext(archivePath))
 
 	switch ext {
@@ -44,6 +59,9 @@ func ExtractArchive(archivePath string) ([]ExtractedFile, error) {
 
 // ExtractArchiveFromReader extracts archive from reader
 func ExtractArchiveFromReader(r io.Reader, filename string) ([]ExtractedFile, error) {
+	if !IsSupportedArchiveFilename(filename) {
+		return nil, fmt.Errorf("unsupported archive format: %s", strings.ToLower(filepath.Ext(filename)))
+	}
 	ext := strings.ToLower(filepath.Ext(filename))
 
 	switch ext {
@@ -60,6 +78,27 @@ func ExtractArchiveFromReader(r io.Reader, filename string) ([]ExtractedFile, er
 	}
 }
 
+// IsSupportedArchiveFilename reports whether filename extension is supported by archive extractor.
+func IsSupportedArchiveFilename(filename string) bool {
+	ext := strings.ToLower(strings.TrimSpace(filepath.Ext(filename)))
+	if ext == "" {
+		return false
+	}
+	_, ok := supportedArchiveExt[ext]
+	return ok
+}
+
+// SupportedArchiveExtensions returns sorted list of archive/file extensions
+// accepted by archive extractor.
+func SupportedArchiveExtensions() []string {
+	out := make([]string, 0, len(supportedArchiveExt))
+	for ext := range supportedArchiveExt {
+		out = append(out, ext)
+	}
+	sort.Strings(out)
+	return out
+}
+
 func extractTarGz(archivePath string) ([]ExtractedFile, error) {
 	f, err := os.Open(archivePath)
 	if err != nil {
@@ -111,6 +150,7 @@ func extractTarFromReader(r io.Reader) ([]ExtractedFile, error) {
 		files = append(files, ExtractedFile{
 			Path:    header.Name,
 			Content: content,
+			ModTime: header.ModTime,
 		})
 	}
 
@@ -152,6 +192,7 @@ func extractTarGzFromReader(r io.Reader, filename string) ([]ExtractedFile, erro
 			file := ExtractedFile{
 				Path:    baseName,
 				Content: decompressed,
+				ModTime: gzr.ModTime,
 			}
 			if gzipTruncated {
 				file.Truncated = true
@@ -180,6 +221,7 @@ func extractTarGzFromReader(r io.Reader, filename string) ([]ExtractedFile, erro
 				files = append(files, ExtractedFile{
 					Path:    header.Name,
 					Content: content,
+					ModTime: header.ModTime,
 				})
 			}
 		}
@@ -230,6 +272,7 @@ func extractZip(archivePath string) ([]ExtractedFile, error) {
 		files = append(files, ExtractedFile{
 			Path:    f.Name,
 			Content: content,
+			ModTime: f.Modified,
 		})
 	}
 
@@ -281,6 +324,7 @@ func extractZipFromReader(r io.Reader) ([]ExtractedFile, error) {
 		files = append(files, ExtractedFile{
 			Path:    f.Name,
 			Content: content,
+			ModTime: f.Modified,
 		})
 	}
 
@@ -288,13 +332,24 @@ func extractZipFromReader(r io.Reader) ([]ExtractedFile, error) {
 }
 
 func extractSingleFile(path string) ([]ExtractedFile, error) {
+	info, err := os.Stat(path)
+	if err != nil {
+		return nil, fmt.Errorf("stat file: %w", err)
+	}
 	f, err := os.Open(path)
 	if err != nil {
 		return nil, fmt.Errorf("open file: %w", err)
 	}
 	defer f.Close()
 
-	return extractSingleFileFromReader(f, filepath.Base(path))
+	files, err := extractSingleFileFromReader(f, filepath.Base(path))
+	if err != nil {
+		return nil, err
+	}
+	if len(files) > 0 {
+		files[0].ModTime = info.ModTime()
+	}
+	return files, nil
 }
 
 func extractSingleFileFromReader(r io.Reader, filename string) ([]ExtractedFile, error) {

internal/parser/archive_test.go

@@ -69,3 +69,25 @@ func TestExtractArchiveFromReaderTXT_TruncatedWhenTooLarge(t *testing.T) {
 		t.Fatalf("expected truncation message")
 	}
 }
+
+func TestIsSupportedArchiveFilename(t *testing.T) {
+	cases := []struct {
+		name string
+		want bool
+	}{
+		{name: "dump.tar.gz", want: true},
+		{name: "nvidia-bug-report-1651124000923.log.gz", want: true},
+		{name: "snapshot.zip", want: true},
+		{name: "report.log", want: true},
+		{name: "xigmanas.txt", want: true},
+		{name: "raw_export.json", want: false},
+		{name: "archive.bin", want: false},
+	}
+
+	for _, tc := range cases {
+		got := IsSupportedArchiveFilename(tc.name)
+		if got != tc.want {
+			t.Fatalf("IsSupportedArchiveFilename(%q)=%v, want %v", tc.name, got, tc.want)
+		}
+	}
+}

internal/parser/parser.go

@@ -66,11 +66,41 @@ func (p *BMCParser) parseFiles() error {
 	result.Filename = p.result.Filename
 
 	appendExtractionWarnings(result, p.files)
+	if result.CollectedAt.IsZero() {
+		if ts := inferCollectedAtFromExtractedFiles(p.files); !ts.IsZero() {
+			result.CollectedAt = ts.UTC()
+		}
+	}
 	p.result = result
 
 	return nil
 }
 
+func inferCollectedAtFromExtractedFiles(files []ExtractedFile) time.Time {
+	var latestReliable time.Time
+	var latestAny time.Time
+	for _, f := range files {
+		ts := f.ModTime
+		if ts.IsZero() {
+			continue
+		}
+		if latestAny.IsZero() || ts.After(latestAny) {
+			latestAny = ts
+		}
+		// Ignore placeholder archive mtimes like 1980-01-01.
+		if ts.Year() < 2000 {
+			continue
+		}
+		if latestReliable.IsZero() || ts.After(latestReliable) {
+			latestReliable = ts
+		}
+	}
+	if !latestReliable.IsZero() {
+		return latestReliable
+	}
+	return latestAny
+}
+
 func appendExtractionWarnings(result *models.AnalysisResult, files []ExtractedFile) {
 	if result == nil {
 		return

internal/parser/parser_test.go

@@ -2,6 +2,7 @@ package parser
 
 import (
 	"testing"
+	"time"
 
 	"git.mchus.pro/mchus/logpile/internal/models"
 )
@@ -32,3 +33,30 @@ func TestAppendExtractionWarnings(t *testing.T) {
 		t.Fatalf("expected warning details in RawData")
 	}
 }
+
+func TestInferCollectedAtFromExtractedFiles_PrefersReliableMTime(t *testing.T) {
+	files := []ExtractedFile{
+		{Path: "a.log", ModTime: time.Date(1980, 1, 1, 0, 0, 0, 0, time.UTC)},
+		{Path: "b.log", ModTime: time.Date(2025, 12, 12, 10, 14, 49, 0, time.FixedZone("EST", -5*3600))},
+		{Path: "c.log", ModTime: time.Date(2026, 2, 28, 4, 18, 18, 0, time.FixedZone("UTC+8", 8*3600))},
+	}
+
+	got := inferCollectedAtFromExtractedFiles(files)
+	want := files[2].ModTime
+	if !got.Equal(want) {
+		t.Fatalf("expected %s, got %s", want, got)
+	}
+}
+
+func TestInferCollectedAtFromExtractedFiles_FallsBackToAnyMTime(t *testing.T) {
+	files := []ExtractedFile{
+		{Path: "a.log", ModTime: time.Date(1980, 1, 1, 0, 0, 0, 0, time.UTC)},
+		{Path: "b.log", ModTime: time.Date(1970, 1, 2, 0, 0, 0, 0, time.UTC)},
+	}
+
+	got := inferCollectedAtFromExtractedFiles(files)
+	want := files[0].ModTime
+	if !got.Equal(want) {
+		t.Fatalf("expected fallback %s, got %s", want, got)
+	}
+}

internal/parser/vendors/inspur/parser.go

@@ -8,6 +8,7 @@ package inspur
 import (
 	"fmt"
 	"strings"
+	"time"
 
 	"git.mchus.pro/mchus/logpile/internal/models"
 	"git.mchus.pro/mchus/logpile/internal/parser"
@@ -86,6 +87,8 @@ func containsInspurMarkers(content []byte) bool {
 
 // Parse parses Inspur/Kaytus archive
 func (p *Parser) Parse(files []parser.ExtractedFile) (*models.AnalysisResult, error) {
+	selLocation := inferInspurArchiveLocation(files)
+
 	result := &models.AnalysisResult{
 		Events:  make([]models.Event, 0),
 		FRU:     make([]models.FRUInfo, 0),
@@ -145,7 +148,7 @@ func (p *Parser) Parse(files []parser.ExtractedFile) (*models.AnalysisResult, er
 
 	// Parse SEL list (selelist.csv)
 	if f := parser.FindFileByName(files, "selelist.csv"); f != nil {
-		selEvents := ParseSELList(f.Content)
+		selEvents := ParseSELListWithLocation(f.Content, selLocation)
 		result.Events = append(result.Events, selEvents...)
 	}
 
@@ -184,6 +187,43 @@ func (p *Parser) Parse(files []parser.ExtractedFile) (*models.AnalysisResult, er
 	return result, nil
 }
 
+func inferInspurArchiveLocation(files []parser.ExtractedFile) *time.Location {
+	fallback := parser.DefaultArchiveLocation()
+	f := parser.FindFileByName(files, "timezone.conf")
+	if f == nil {
+		return fallback
+	}
+	locName := parseTimezoneConfigLocation(f.Content)
+	if strings.TrimSpace(locName) == "" {
+		return fallback
+	}
+	loc, err := time.LoadLocation(locName)
+	if err != nil {
+		return fallback
+	}
+	return loc
+}
+
+func parseTimezoneConfigLocation(content []byte) string {
+	lines := strings.Split(string(content), "\n")
+	for _, line := range lines {
+		line = strings.TrimSpace(line)
+		if line == "" || strings.HasPrefix(line, "[") || strings.HasPrefix(line, "#") || strings.HasPrefix(line, ";") {
+			continue
+		}
+		parts := strings.SplitN(line, "=", 2)
+		if len(parts) != 2 {
+			continue
+		}
+		key := strings.ToLower(strings.TrimSpace(parts[0]))
+		val := strings.TrimSpace(parts[1])
+		if key == "timezone" && val != "" {
+			return val
+		}
+	}
+	return ""
+}
+
 func (p *Parser) parseDeviceFruSDR(content []byte, result *models.AnalysisResult) {
 	lines := string(content)
 

internal/parser/vendors/inspur/sel.go

@@ -13,6 +13,12 @@ import (
 // Format: ID, Date (MM/DD/YYYY), Time (HH:MM:SS), Sensor, Event, Status
 // Example: 1,04/18/2025,09:31:18,Event Logging Disabled SEL_Status,Log area reset/cleared,Asserted
 func ParseSELList(content []byte) []models.Event {
+	return ParseSELListWithLocation(content, parser.DefaultArchiveLocation())
+}
+
+// ParseSELListWithLocation parses selelist.csv using provided source timezone
+// for timestamps that don't contain an explicit offset.
+func ParseSELListWithLocation(content []byte, location *time.Location) []models.Event {
 	var events []models.Event
 
 	text := string(content)
@@ -49,7 +55,7 @@ func ParseSELList(content []byte) []models.Event {
 		status := strings.TrimSpace(records[5])
 
 		// Parse timestamp: MM/DD/YYYY HH:MM:SS
-		timestamp := parseSELTimestamp(dateStr, timeStr)
+		timestamp := parseSELTimestamp(dateStr, timeStr, location)
 
 		// Extract sensor type and name
 		sensorType, sensorName := parseSensorInfo(sensorStr)
@@ -77,12 +83,16 @@ func ParseSELList(content []byte) []models.Event {
 }
 
 // parseSELTimestamp parses MM/DD/YYYY and HH:MM:SS into time.Time
-func parseSELTimestamp(dateStr, timeStr string) time.Time {
+func parseSELTimestamp(dateStr, timeStr string, location *time.Location) time.Time {
 	// Combine date and time: MM/DD/YYYY HH:MM:SS
 	timestampStr := dateStr + " " + timeStr
 
+	if location == nil {
+		location = parser.DefaultArchiveLocation()
+	}
+
 	// Try parsing with MM/DD/YYYY format
-	t, err := parser.ParseInDefaultArchiveLocation("01/02/2006 15:04:05", timestampStr)
+	t, err := time.ParseInLocation("01/02/2006 15:04:05", timestampStr, location)
 	if err != nil {
 		// Fallback to current time
 		return time.Now()

internal/parser/vendors/inspur/sel_test.go

@@ -0,0 +1,33 @@
+package inspur
+
+import (
+	"testing"
+	"time"
+)
+
+func TestParseSELListWithLocation_UsesProvidedTimezone(t *testing.T) {
+	content := []byte("sel elist:\n1,02/28/2026,04:18:18,Sensor X,Event,Asserted\n")
+	shanghai, err := time.LoadLocation("Asia/Shanghai")
+	if err != nil {
+		t.Fatalf("load location: %v", err)
+	}
+
+	events := ParseSELListWithLocation(content, shanghai)
+	if len(events) != 1 {
+		t.Fatalf("expected 1 event, got %d", len(events))
+	}
+
+	// 04:18:18 +08:00 == 20:18:18Z (previous day)
+	want := time.Date(2026, 2, 27, 20, 18, 18, 0, time.UTC)
+	if !events[0].Timestamp.UTC().Equal(want) {
+		t.Fatalf("unexpected timestamp: got %s want %s", events[0].Timestamp.UTC(), want)
+	}
+}
+
+func TestParseTimezoneConfigLocation(t *testing.T) {
+	content := []byte("[TimeZoneConfig]\ntimezone=Asia/Shanghai\n")
+	got := parseTimezoneConfigLocation(content)
+	if got != "Asia/Shanghai" {
+		t.Fatalf("unexpected timezone: %q", got)
+	}
+}

internal/parser/vendors/nvidia_bug_report/parser.go

@@ -3,14 +3,33 @@
 package nvidia_bug_report
 
 import (
+	"fmt"
+	"regexp"
 	"strings"
+	"time"
 
 	"git.mchus.pro/mchus/logpile/internal/models"
 	"git.mchus.pro/mchus/logpile/internal/parser"
 )
 
 // parserVersion - version of this parser module
-const parserVersion = "1.0.0"
+const parserVersion = "1.1.0"
+
+var bugReportDateLineRegex = regexp.MustCompile(`(?m)^Date:\s+(.+?)\s*$`)
+var dateWithTZAbbrevRegex = regexp.MustCompile(`^([A-Za-z]{3}\s+[A-Za-z]{3}\s+\d{1,2}\s+\d{2}:\d{2}:\d{2})\s+([A-Za-z]{2,5})\s+(\d{4})$`)
+
+var timezoneAbbrevToOffset = map[string]string{
+	"UTC": "+00:00",
+	"GMT": "+00:00",
+	"EST": "-05:00",
+	"EDT": "-04:00",
+	"CST": "-06:00",
+	"CDT": "-05:00",
+	"MST": "-07:00",
+	"MDT": "-06:00",
+	"PST": "-08:00",
+	"PDT": "-07:00",
+}
 
 func init() {
 	parser.Register(&Parser{})
@@ -81,6 +100,10 @@ func (p *Parser) Parse(files []parser.ExtractedFile) (*models.AnalysisResult, er
 	}
 
 	content := string(files[0].Content)
+	if collectedAt, tzOffset, ok := parseBugReportCollectedAt(content); ok {
+		result.CollectedAt = collectedAt.UTC()
+		result.SourceTimezone = tzOffset
+	}
 
 	// Parse system information
 	parseSystemInfo(content, result)
@@ -105,3 +128,49 @@ func (p *Parser) Parse(files []parser.ExtractedFile) (*models.AnalysisResult, er
 
 	return result, nil
 }
+
+func parseBugReportCollectedAt(content string) (time.Time, string, bool) {
+	matches := bugReportDateLineRegex.FindStringSubmatch(content)
+	if len(matches) != 2 {
+		return time.Time{}, "", false
+	}
+	raw := strings.TrimSpace(matches[1])
+	if raw == "" {
+		return time.Time{}, "", false
+	}
+
+	if m := dateWithTZAbbrevRegex.FindStringSubmatch(raw); len(m) == 4 {
+		if offset, ok := timezoneAbbrevToOffset[strings.ToUpper(strings.TrimSpace(m[2]))]; ok {
+			layout := "Mon Jan 2 15:04:05 -07:00 2006"
+			normalized := strings.TrimSpace(m[1]) + " " + offset + " " + strings.TrimSpace(m[3])
+			if ts, err := time.Parse(layout, normalized); err == nil {
+				return ts, offset, true
+			}
+		}
+	}
+
+	layouts := []string{
+		"Mon Jan 2 15:04:05 MST 2006",
+		"Mon Jan 2 15:04:05 2006",
+	}
+	for _, layout := range layouts {
+		ts, err := time.Parse(layout, raw)
+		if err != nil {
+			continue
+		}
+		return ts, formatOffset(ts), true
+	}
+	return time.Time{}, "", false
+}
+
+func formatOffset(t time.Time) string {
+	_, sec := t.Zone()
+	sign := '+'
+	if sec < 0 {
+		sign = '-'
+		sec = -sec
+	}
+	h := sec / 3600
+	m := (sec % 3600) / 60
+	return fmt.Sprintf("%c%02d:%02d", sign, h, m)
+}

internal/parser/vendors/nvidia_bug_report/parser_test.go

@@ -0,0 +1,54 @@
+package nvidia_bug_report
+
+import (
+	"testing"
+	"time"
+
+	"git.mchus.pro/mchus/logpile/internal/parser"
+)
+
+func TestParseBugReportCollectedAt(t *testing.T) {
+	content := `
+Start of NVIDIA bug report log file
+Date: Fri Dec 12 10:14:49 EST 2025
+`
+
+	got, tz, ok := parseBugReportCollectedAt(content)
+	if !ok {
+		t.Fatalf("expected collected_at to be parsed")
+	}
+	if tz != "-05:00" {
+		t.Fatalf("expected tz offset -05:00, got %q", tz)
+	}
+	wantUTC := time.Date(2025, 12, 12, 15, 14, 49, 0, time.UTC)
+	if !got.UTC().Equal(wantUTC) {
+		t.Fatalf("expected %s, got %s", wantUTC, got.UTC())
+	}
+}
+
+func TestNvidiaBugReportParser_SetsCollectedAtAndTimezone(t *testing.T) {
+	p := &Parser{}
+	files := []parser.ExtractedFile{
+		{
+			Path: "nvidia-bug-report-1653925023938.log",
+			Content: []byte(`
+Start of NVIDIA bug report log file
+nvidia-bug-report.sh Version: 34275561
+Date: Fri Dec 12 10:14:49 EST 2025
+`),
+		},
+	}
+
+	result, err := p.Parse(files)
+	if err != nil {
+		t.Fatalf("parse failed: %v", err)
+	}
+
+	if result.SourceTimezone != "-05:00" {
+		t.Fatalf("expected source timezone -05:00, got %q", result.SourceTimezone)
+	}
+	wantUTC := time.Date(2025, 12, 12, 15, 14, 49, 0, time.UTC)
+	if !result.CollectedAt.Equal(wantUTC) {
+		t.Fatalf("expected collected_at %s, got %s", wantUTC, result.CollectedAt)
+	}
+}